updations to the finbert function

app.py

@@ -107,7 +107,7 @@ def finbert(word):
         data['Cluster'] = pd.Series(assigned_clusters, index = data.index)
         data['Centroid'] = data['Cluster'].apply(lambda x: Kclusterer.means()[x])
     
-    # return the text if the clustering algorithm catches an exception and move to the next text file
+    # return the text if clustering algorithm catches an exceptiona and move to the next text file
     except ValueError:
         return text
 
@@ -122,10 +122,17 @@ def finbert(word):
     summary = " ".join(data.sort_values(
                 'Distance_From_Centroid',
                 ascending = True).groupby('Cluster').head(1).sort_index()['Sentences'].tolist())
-    return (summary,"    Length of Input:---->"+str(len(word)),"  Length of Output:----> "+str(len(summary)))
+    import re
+    words = list()
+    for text in summary.split():
+            text = re.sub(r'\n','',text)
+            text = re.sub(r'\s$','',text)
+            words.append(text)
+    summary = " ".join(words)
+
+    return  (summary,len(word),len(summary))
     
 
-
 def pegasus(text):
     '''A function to obtain summaries for each tokenized sentence.
     It returns a summarized document as output'''